Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare non-read-only, non-idempotent, destructive; the description adds a great deal more: state is preserved for movement and saved dates, exactly one activity event is created, account/credential restrictions apply, invalid state is refused with conflict, and repetition can fail the state guard or duplicate events after intervening moves. That last point is essential non-idempotency context an agent cannot infer from the hints alone.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Every sentence carries non-redundant information and the operation is front-loaded in the first clause. It is readable rather than maximal, but it is a single dense block with the retry/error guidance buried at the end and no structure; a slight break would improve scanning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Although an output schema exists and return values need not be restated, the description still flags the ten-evidence / ten-prompt-reference cap and cursor behavior, which is exactly the kind of truncation detail that changes how an agent calls get_recommendation next. Combined with conflict handling and retry semantics, nothing material is missing for a 2-parameter state-mutating tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and both UUID parameters are documented with their source tools (list_sites_and_topics, get_recommendations), so the baseline is 3. The description adds the state requirement attached to recommendationId but no format or syntax detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Record that work has started on an approved recommendation') plus the exact state transition (approved -> underway), which distinguishes it from siblings like approve_recommendation, archive_recommendation, and get_recommendation. An agent can identify the operation without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit precondition ('Requires approved'), explicit alternative for cursor continuation ('continue non-null cursors using get_recommendation'), and an explicit retry protocol ('After uncertain delivery or readback failure, inspect get_recommendation before retrying'). This is when-to-use, when-not-to-retry, and the alternative, all named.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.